Blob Blame History Raw
From c75db84cef6d2990149d2bb549849014d93c6427 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 13 Jan 2022 10:13:51 -0800
Subject: drm/i915/guc: Remove hacks for reset and schedule disable G2H being
 received out of order
Git-commit: 41f8aa5d6a8aace5d33e2d908bf5fdc833456a5f
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

In the i915 there are several hacks in place to make request cancellation
work with an old version of the GuC which delivered the G2H indicating
schedule disable is done before G2H indicating a context reset. Version
69 fixes this, so we can remove these hacks.

v2:
 (Checkpatch)
  - s/cancelation/cancellation

Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220113181351.21296-3-matthew.brost@intel.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 30 ++-----------------
 1 file changed, 2 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 1f4003be1f40..9cb700984e2a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1613,7 +1613,6 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	unsigned long flags;
 	u32 head;
 	int i, number_children = ce->parallel.number_children;
-	bool skip = false;
 	struct intel_context *parent = ce;
 
 	GEM_BUG_ON(intel_context_is_child(ce));
@@ -1624,23 +1623,10 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	 * GuC will implicitly mark the context as non-schedulable when it sends
 	 * the reset notification. Make sure our state reflects this change. The
 	 * context will be marked enabled on resubmission.
-	 *
-	 * XXX: If the context is reset as a result of the request cancellation
-	 * this G2H is received after the schedule disable complete G2H which is
-	 * wrong as this creates a race between the request cancellation code
-	 * re-submitting the context and this G2H handler. This is a bug in the
-	 * GuC but can be worked around in the meantime but converting this to a
-	 * NOP if a pending enable is in flight as this indicates that a request
-	 * cancellation has occurred.
 	 */
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
-	if (likely(!context_pending_enable(ce)))
-		clr_context_enabled(ce);
-	else
-		skip = true;
+	clr_context_enabled(ce);
 	spin_unlock_irqrestore(&ce->guc_state.lock, flags);
-	if (unlikely(skip))
-		goto out_put;
 
 	/*
 	 * For each context in the relationship find the hanging request
@@ -1672,7 +1658,6 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
 	}
 
 	__unwind_incomplete_requests(parent);
-out_put:
 	intel_context_put(parent);
 }
 
@@ -2612,12 +2597,6 @@ static void guc_context_cancel_request(struct intel_context *ce,
 					true);
 		}
 
-		/*
-		 * XXX: Racey if context is reset, see comment in
-		 * __guc_reset_context().
-		 */
-		flush_work(&ce_to_guc(ce)->ct.requests.worker);
-
 		guc_context_unblock(block_context);
 		intel_context_put(ce);
 	}
@@ -4052,12 +4031,7 @@ static void guc_handle_context_reset(struct intel_guc *guc,
 {
 	trace_intel_context_reset(ce);
 
-	/*
-	 * XXX: Racey if request cancellation has occurred, see comment in
-	 * __guc_reset_context().
-	 */
-	if (likely(!intel_context_is_banned(ce) &&
-		   !context_blocked(ce))) {
+	if (likely(!intel_context_is_banned(ce))) {
 		capture_error_state(guc, ce);
 		guc_context_replay(ce);
 	} else {
-- 
2.38.1